Click on “Download PDF” for the PDF version or on the title for the HTML version.


If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Sea fish identification using convolutional neural network

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  2017 ASABE Annual International Meeting  1700752.(doi:10.13031/aim.201700752)
Authors:   Chen Tung, Ching-Lu Hsieh, Yan-Fu Kuo
Keywords:   Convolutional neural network, fish catch, identification, transfer learning.

Abstract. In recent years, international organizations have regulated fishery in public seas to conserve marine ecosystems. Automatically identifying the types of fish catch is one of the most impartial approaches for monitoring fishing practices. Hence, this study proposes the use of image processing and deep learning algorithms to automatically identify deep-sea fish. Two convolutional neural network classifiers were developed to differentiate fish into four classes: tuna, billfish, shark, and others. During this process, two pre-trained models were employed as the base network and then fine-tuned to improve the identification ability when facing fine-grained-image classification problems. The experimental results show that these four classes of fish can be identified with a relatively high degree of accuracy (94.5% for the VGG16-based classifier and 92.25% for the Inception-V3-based classifier).

(Download PDF)    (Export to EndNotes)